يمكن أن ترجمت نماذج النص العصبي المؤقتة مؤخرا لترجمة أسئلة اللغة الطبيعية بفعالية لاستعلامات SQL المقابلة على قواعد البيانات غير المرئية.العمل في الغالب على مجموعة بيانات العنكبوت، اقترح الباحثون حلولا متطورة بشكل متزايد للمشكلة.على عكس هذا الاتجاه، في هذه الورقة نركز على التبسيط.نبدأ بإعادة بناء DUORAT، وإعادة تنفيذ طراز Rat-Art-Art-Art الذي يعكس RAT-SQL باستخدام محولات العلاقات أو الفانيليا فقط كقطات بناء.نحن نؤدي العديد من التجارب الاجتثاث باستخدام Duorat كنموذج الأساس.تقوم تجاربنا بتأكيد فائدة بعض التقنيات وأشرح التكرار للآخرين، بما في ذلك ميزات وميزات SQL الهيكلية التي ترتبط بالسؤال مع المخطط.
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the problem. Contrary to this trend, in this paper we focus on simplifications. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.
References used
https://aclanthology.org/
Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of
Learning to capture text-table alignment is essential for tasks like text-to-SQL. A model needs to correctly recognize natural language references to columns and values and to ground them in the given database schema. In this paper, we present a nove
Existing approaches for machine translation (MT) mostly translate given text in the source language into the target language and without explicitly referring to information indispensable for producing proper translation. This includes not only inform
Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specif
Strong and affordable in-domain data is a desirable asset when transferring trained semantic parsers to novel domains. As previous methods for semi-automatically constructing such data cannot handle the complexity of realistic SQL queries, we propose